© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104053
    Prev
    Next
    INDEX
    Explanations

    technical syntax and code structure, particularly in programming and data management contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Programming language identifiers, variable names, property accessors, and path elements in code snippets.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     revêtement
    -0.39
     Leh
    -0.30
      
    -0.29
     Jack
    -0.29
     classes
    -0.28
    <tbody>
    -0.28
     polyp
    -0.27
    HomeAsUp
    -0.27
     colegios
    -0.27
     frequency
    -0.27
    POSITIVE LOGITS
    uxxxx
    0.84
    RenderAtEndOf
    0.83
    fromnode
    0.79
    ########.
    0.74
     للمعارف
    0.74
    ſt
    0.73
    MessageOf
    0.70
    帖最后由
    0.69
    contentLoaded
    0.69
    tonode
    0.67
    Activations Density 0.057%

    No Known Activations